Viz_plot

library(ggplot2)
options(scipen=999) # turn-off scientific notation like 1e+48
theme_set(theme_bw()) # pre-set the bw theme.
data("midwest", package = "ggplot2")
# ALT way: midwest <- read.csv("http://goo.gl/G1K41K")

• geom_bar() Bar chart color, fill, alpha
• geom_boxplot() Box plot color, fill, alpha, notch, width
• geom_density() Density plot color, fill, alpha, linetype
• geom_histogram() Histogram color, fill, alpha, linetype, binwidth
• geom_hline() Horizontal lines color, alpha, linetype, size
• geom_jitter() Jittered points color, size, alpha, shape
• geom_line() Line graph colorvalpha, linetype, size
• geom_point() Scatterplot color, alpha, shape, size
• geom_rug() Rug plot color, side
• geom_smooth() Fitted line method, formula, color, fill, linetype, size
• geom_text() Text annotations Many; see the help for this function
• geom_violin() Violin plot color, fill, alpha, linetype

• geom_vline() Vertical lines color, alpha, linetype, size

• color: colour of points, lines, and borders around filled regions
• fill: colour of filled areas such as bars and density regions
• alpha: transparency of colors, ranging from 0 (fully transparent) to 1 (opaque)
• linetype: pattern for lines (1 = solid, 2 = dashed, 3 = dotted, 4 = dotdash, 5 = longdash, 6 = * twodash)
• size: point size and line width
• shape: point shapes (same as pch, with 0 = open square, 1 = open circle, 2 = open triangle, and so on)
• position: position of plotted objects such as bars and points. For bars, “dodge” places grouped bar charts, side by side, “stacked” vertically stacks grouped bar charts, and “fill” vertically stacks grouped bar charts and standardizes their heights to be equal; for points, “jitter” reduces point overlap
• binwidth: bin width for histograms
• notch: indicates whether box plots should be notched (TRUE/FALSE)
• sides: placement of rug plots on the graph (“b” = bottom, “l” = left, “t” = top, “r” = right, “bl” = both bottom and left, and so on)

• width: width of box plots

1 Animation Plot

library(ggplot2)
library(plotly)
data(gapminder, package = "gapminder")
gg <- ggplot(gapminder, aes(gdpPercap, lifeExp, color = continent)) +
  geom_point(aes(size = pop, frame = year, ids = country)) +
  scale_x_log10()
ggplotly(gg)

base <- gapminder %>%
  plot_ly(x = ~gdpPercap, y = ~lifeExp, size = ~pop, 
          text = ~country, hoverinfo = "text") %>%
  layout(xaxis = list(type = "log"))

base %>%
  add_markers(color = ~continent, frame = ~year, ids = ~country) %>%
  animation_opts(1000, easing = "elastic", redraw = FALSE) %>%
  animation_button(
    x = 1, xanchor = "right", y = 0, yanchor = "bottom"
  ) %>%
  animation_slider(
    currentvalue = list(prefix = "YEAR ", font = list(color="red"))
  )

meanLife <- with(gapminder, tapply(lifeExp, INDEX = continent, mean))
gapminder$continent <- factor(
  gapminder$continent, levels = names(sort(meanLife))
)

base %>%
  add_markers(data = gapminder, frame = ~continent) %>%
  hide_legend() %>%
  animation_opts(frame = 1000, transition = 0, redraw = FALSE)

base %>%
  add_markers(color = ~continent, alpha = 0.2, alpha_stroke = 0.2, showlegend = F) %>%
  add_markers(color = ~continent, frame = ~year, ids = ~country) %>%
  animation_opts(1000, redraw = FALSE)

2 Scatterplot

library(ggplot2)
ggplot(mpg, aes(x=cty, y=hwy, color=class, shape=class)) +
  geom_point() +
  facet_grid(.~trans)

## Warning: The shape palette can deal with a maximum of 6 discrete values
## because more than 6 becomes difficult to discriminate; you have 7.
## Consider specifying shapes manually if you must have them.

## Warning: Removed 62 rows containing missing values (geom_point).

ggplot(mpg, aes(cty, hwy)) + geom_point(aes(colour = class))

ggplot(mpg, aes(cty, hwy)) + geom_point(colour = "red") # having one color througout

gg <- ggplot(midwest, aes(x=area, y=poptotal)) +
geom_point(aes(col=state, size=popdensity)) +
geom_smooth(method="loess", se=F) +
xlim(c(0, 0.1)) +
ylim(c(0, 500000)) +
labs(subtitle="Area Vs Population", y="Population",
       x="Area",
       title="Scatterplot",
       caption = "Source: midwest")
plot(gg)

## Warning: Removed 15 rows containing non-finite values (stat_smooth).

## Warning: Removed 15 rows containing missing values (geom_point).

2.1 Scatterplot With Encircling

This can be conveniently done using the geom_encircle() in ggalt package.

options(scipen = 999)
library(ggplot2)
library(ggalt)
midwest_select <- midwest[midwest$poptotal > 350000 &
                            midwest$poptotal <= 500000 &
                            midwest$area > 0.01 &
                            midwest$area < 0.1, ]

# Plot
ggplot(midwest, aes(x=area, y=poptotal)) +
geom_point(aes(col=state, size=popdensity)) +
geom_smooth(method="loess", se=F) +
xlim(c(0, 0.1)) +
ylim(c(0, 500000)) + # draw smoothing line 
  geom_encircle(aes(x=area, y=poptotal),
                data=midwest_select,
                color="red",
                size=2,
                expand=0.08) +   # encircle
labs(subtitle="Area Vs Population", y="Population",
       x="Area",
       title="Scatterplot + Encircle",
       caption="Source: midwest")

## Warning: Removed 15 rows containing non-finite values (stat_smooth).

## Warning: Removed 15 rows containing missing values (geom_point).

3 Jitter Plot

library(ggplot2)
data(mpg, package="ggplot2") # alternate source: "http://goo.gl/uEeRGu") 
theme_set(theme_bw()) # pre-set the bw theme.
g <- ggplot(mpg, aes(cty, hwy))

# Scatterplot
g + geom_point() +
geom_smooth(method="lm", se=F) + 
  labs(subtitle="mpg: city vs highway mileage",
       y="hwy",
       x="cty",
       title="Scatterplot with overlapping points",
       caption="Source: midwest")

# load package and data
library(ggplot2)
data(mpg, package="ggplot2") # mpg <- read.csv("http://goo.gl/uEeRGu")
# Scatterplot
theme_set(theme_bw()) # pre-set the bw theme. 
g <- ggplot(mpg, aes(cty, hwy))
g + geom_jitter(width = .5, size=1) +
labs(subtitle="mpg: city vs highway mileage", y="hwy",
       x="cty",
       title="Jittered Points")

4 Counts Chart

# load package and data
library(ggplot2)
data(mpg, package="ggplot2")
# mpg <- read.csv("http://goo.gl/uEeRGu")
# Scatterplot
theme_set(theme_bw()) # pre-set the bw theme. g <- ggplot(mpg, aes(cty, hwy))
g + geom_count(col="tomato3", show.legend=F) +
labs(subtitle="mpg: city vs highway mileage", y="hwy",
       x="cty",
       title="Counts Plot")

5 Bubble plot

# load package and data
library(ggplot2)
data(mpg, package="ggplot2")
# mpg <- read.csv("http://goo.gl/uEeRGu")
mpg_select <- mpg[mpg$manufacturer %in% c("audi", "ford", "honda", "hyundai"), ]
# Scatterplot
theme_set(theme_bw()) # pre-set the bw theme. 
g <- ggplot(mpg_select, aes(displ, cty)) +
labs(subtitle="mpg: Displacement vs City Mileage", title="Bubble chart")
g + geom_jitter(aes(col=manufacturer, size=hwy)) + geom_smooth(aes(col=manufacturer), method="lm", se=F)

6 Gganimate

library(ggplot2)
library(gganimate)

## Warning: package 'gganimate' was built under R version 3.5.2

library(gapminder)

## 
## Attaching package: 'gapminder'

## The following object is masked _by_ '.GlobalEnv':
## 
##     gapminder

theme_set(theme_bw()) # pre-set the bw theme.
g <- ggplot(gapminder, aes(gdpPercap, lifeExp, size = pop, frame = year)) + 
  geom_point() +
geom_smooth(aes(group = year),
              method = "lm",
show.legend = FALSE) +
  facet_wrap(~continent, scales = "free") +
scale_x_log10() # convert to log scale 
# gganimate(g, interval=0.2)

7 Marginal Histogram / Boxplot

library(ggplot2)
library(ggExtra)
theme_set(theme_bw()) # pre-set the bw theme.
data(mpg, package="ggplot2") # mpg <- read.csv("http://goo.gl/uEeRGu")

# Scatterplot
mpg_select <- mpg[mpg$hwy >= 35 & mpg$cty > 27, ]
g <- ggplot(mpg, aes(cty, hwy)) +
geom_count() +
geom_smooth(method="lm", se=F)
ggMarginal(g, type = "histogram", fill="transparent")
ggMarginal(g, type = "boxplot", fill="transparent")
ggMarginal(g, type = "density", fill="transparent")

g

8 Correlogram

library(ggplot2)
library(ggcorrplot)
# Correlation matrix data(mtcars)
corr <- round(cor(mtcars), 1)
# Plot
ggcorrplot(corr, hc.order = TRUE,
type = "lower",
lab = TRUE,
lab_size = 3,
method="circle",
colors = c("tomato2", "white", "springgreen3"), title="Correlogram of mtcars", ggtheme=theme_bw)

9 B. Deviation/Diverging Bars

library(ggplot2) 
theme_set(theme_bw())

# Data Prep
data("mtcars") # load data
mtcars$`car name` <- rownames(mtcars) # create new column for car names
mtcars$mpg_z <- round((mtcars$mpg - mean(mtcars$mpg))/sd(mtcars$mpg), 2) # compute normalized mpg
mtcars$mpg_type <- ifelse(mtcars$mpg_z < 0, "below", "above") # above / below avg flag 
mtcars <- mtcars[order(mtcars$mpg_z), ] # sort
mtcars$`car name` <- factor(mtcars$`car name`, levels = mtcars$`car name`) # convert to factor to retain sorted order in plot.

# Diverging Barcharts
ggplot(mtcars, aes(x=`car name`, y=mpg_z, label=mpg_z)) +
geom_bar(stat='identity', aes(fill=mpg_type), width=.5) + scale_fill_manual(name="Mileage",
labels = c("Above Average", "Below Average"),
values = c("above"="#00ba38", "below"="#f8766d")) + labs(subtitle="Normalised mileage from 'mtcars'",
title= "Diverging Bars") + coord_flip()

library(ggplot2)
theme_set(theme_bw())
data("mtcars") # load data
mtcars$'car name' <- rownames(mtcars) # create new column for car names
mtcars$mpg_z <- round((mtcars$mpg - mean(mtcars$mpg))/sd(mtcars$mpg), 2) # compute normalized mpg
mtcars$mpg_type <- ifelse(mtcars$mpg_z <0, "below", "above") # above / below avg flag
mtcars <- mtcars[order(mtcars$mpg_z), ] # sort
mtcars$'car name' <- factor(mtcars$'car name', levels = mtcars$'car name')

# convert to factor to retain sorted order in plot.
# Diverging Barcharts
ggplot(mtcars, aes(x='car name', y=mpg_z, label=mpg_z)) +
  geom_bar(stat='identity', aes(fill=mpg_type), width=.5) +
  scale_fill_manual(name="Mileage",
                    labels = c("Above Average", "Below Average"),
                    values = c("above"="#00ba38", "below"="#f8766d")) +
  labs(subtitle="Normalised mileage",
          title= "Diverging Bars - mtcars") +
  coord_flip()

10 Diverging Lollipop Chart

library(ggplot2) 
theme_set(theme_bw())
ggplot(mtcars, aes(x=`car name`, y=mpg_z, label=mpg_z)) +
  geom_point(stat='identity', fill="black", size=6) + 
  geom_segment(aes(y = 0,
                   x = `car name`,
                   yend = mpg_z,
                   xend = `car name`),
color = "black") + geom_text(color="white", size=2) +
labs(title="Diverging Lollipop Chart",
subtitle="Normalized mileage from 'mtcars': Lollipop") +
ylim(-2.5, 2.5) + coord_flip()

11 Diverging Dot Plot

library(ggplot2) 
theme_set(theme_bw())
# Plot
ggplot(mtcars, aes(x=`car name`, y=mpg_z, label=mpg_z)) +
geom_point(stat='identity', aes(col=mpg_type), size=6) +
scale_color_manual(name="Mileage",
labels = c("Above Average", "Below Average"),
values = c("above"="#00ba38", "below"="#f8766d")) + 
geom_text(color="white", size=2) +
labs(title="Diverging Dot Plot",
subtitle="Normalized mileage from 'mtcars': Dotplot") +
ylim(-2.5, 2.5) +
coord_flip()

12 Area Chart

library(ggplot2)
library(quantmod)
data("economics", package = "ggplot2")
# Compute % Returns
economics$returns_perc <- c(0, diff(economics$psavert)/economics$psavert[-length(economics $psavert)])
# Create break points and labels for axis ticks
brks <- economics$date[seq(1, length(economics$date), 12)]
lbls <- lubridate::year(economics$date[seq(1, length(economics$date), 12)])
# Plot
ggplot(economics[1:100, ], aes(date, returns_perc)) +
geom_area() +
scale_x_date(breaks=brks, labels=lbls) +
  theme(axis.text.x = element_text(angle=90)) +
  labs(title="Area Chart",
       subtitle = "Perc Returns for Personal Savings",
       y="% Returns for Personal savings",
       caption="Source: economics")

13 Ranking: Ordered Bar Chart

# Prepare data: group mean city mileage by manufacturer.
cty_mpg <- aggregate(mpg$cty, by=list(mpg$manufacturer), FUN=mean) # aggregate 
colnames(cty_mpg) <- c("make", "mileage") # change column names
cty_mpg <- cty_mpg[order(cty_mpg$mileage), ] # sort
cty_mpg$make <- factor(cty_mpg$make, levels = cty_mpg$make) # to retain the order in plo t.

library(ggplot2) 
theme_set(theme_bw())
# Draw plot
ggplot(cty_mpg, aes(x=make, y=mileage)) +
geom_bar(stat="identity", width=.5, fill="tomato3") + 
  labs(title="Ordered Bar Chart",
       subtitle="Make Vs Avg. Mileage",
caption="source: mpg") +
theme(axis.text.x = element_text(angle=65, vjust=0.6))

14 Lollipop Chart

library(ggplot2) 
theme_set(theme_bw())
# Plot
ggplot(cty_mpg, aes(x=make, y=mileage)) +
geom_point(size=3) + geom_segment(aes(x=make,
                   xend=make,
                   y=0,
                   yend=mileage)) +
labs(title="Lollipop Chart", subtitle="Make Vs Avg. Mileage", caption="source: mpg") +
theme(axis.text.x = element_text(angle=65, vjust=0.6))

15 Dot Plot

library(ggplot2) 
library(scales)
theme_set(theme_classic())
# Plot
ggplot(cty_mpg, aes(x=make, y=mileage)) +
geom_point(col="tomato2", size=3) + # Draw points
geom_segment(aes(x=make, xend=make, y=min(mileage), yend=max(mileage)), linetype="dashed",  size=0.1) + # Draw dashed lines
  labs(title="Dot Plot",
     subtitle="Make Vs Avg. Mileage",
caption="source: mpg") + coord_flip()

16 Slope Chart:

library(ggplot2) 
library(scales)
theme_set(theme_classic())

# prep data
df <- read.csv("https://raw.githubusercontent.com/shahnp/data/master/gdppercap.txt")
colnames(df) <- c("continent", "1952", "1957")
left_label <- paste(df$continent, round(df$`1952`),sep=", ")
right_label <- paste(df$continent, round(df$`1957`),sep=", ")
df$class <- ifelse((df$`1957` - df$`1952`) < 0, "red", "green")

# Plot
p <- ggplot(df) +
  geom_segment(aes(x=1, xend=2, y=`1952`, yend=`1957`, col=class), size=.75,show.legend=F) +
  geom_vline(xintercept=1, linetype="dashed", size=.1) + 
  geom_vline(xintercept=2, linetype="dashed", size=.1) + 
  scale_color_manual(labels = c("Up", "Down"),
                      values = c("green"="#00ba38", "red"="#f8766d")) +
  labs(x="", y="Mean GdpPerCap") + # Axis labels
xlim(.5, 2.5) + ylim(0,(1.1*(max(df$`1952`, df$`1957`)))) # X and Y axis label
  
# Add texts
p <- p + geom_text(label=left_label, y=df$`1952`, x=rep(1, NROW(df)), hjust=1.1, size=3.5)
p <- p + geom_text(label=right_label, y=df$`1957`, x=rep(2, NROW(df)), hjust=-0.1, size=3.5)
p <- p + geom_text(label="Time 1", x=1, y=1.1*(max(df$`1952`, df$`1957`)), hjust=1.2, size =5) # title
p <- p + geom_text(label="Time 2", x=2, y=1.1*(max(df$`1952`, df$`1957`)), hjust=-0.1, size=5) # title
# Minify theme
p + theme(panel.background = element_blank(),
panel.grid = element_blank(), axis.ticks = element_blank(), axis.text.x = element_blank(), panel.border = element_blank(), plot.margin = unit(c(1,2,1,2), "cm"))

17 Dumbbell Plot

library(ggalt)
theme_set(theme_classic())
health <- read.csv("https://raw.githubusercontent.com/shahnp/data/master/health.txt")
health$Area <-factor(health$Area, levels=as.character(health$Area)) # for right ordering of the dumbells
health$Area <- factor(health$Area)
gg <- ggplot(health, aes(x=pct_2013, xend=pct_2014, y=Area, group=Area)) +
geom_dumbbell(color="#a3c4dc", size=0.75) + scale_x_continuous(label=percent) +
  labs(x=NULL, y=NULL,
             title="Dumbbell Chart",
             subtitle="Pct Change: 2013 vs 2014") +
theme(plot.title = element_text(hjust=0.5, face="bold"), plot.background=element_rect(fill="#f7f7f7"), panel.background=element_rect(fill="#f7f7f7"), panel.grid.minor=element_blank(), panel.grid.major.y=element_blank(), panel.grid.major.x=element_line(), axis.ticks=element_blank(),
legend.position="top", panel.border=element_blank())

plot(gg)

D. Distribution

18 Histogram

library("ggplot2")
data(singer, package="lattice")

# Histogram
ggplot(singer, aes(x=height)) +geom_histogram()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

library(ggplot2)
theme_set(theme_classic())
# Histogram on a Continuous (Numeric) Variable
g <- ggplot(mpg, aes(displ)) +
  scale_fill_brewer(palette = "Spectral")
g + geom_histogram(aes(fill=class), binwidth = .1,col="black",size=.1) + # change binwidth
  labs(title="Histogram with Auto Binning",
       subtitle="Engine Displacement across Vehicle Classes")

g + geom_histogram(aes(fill=class), bins=5,col="black",size=.1) + # change number of bins
  labs(title="Histogram with Fixed Bins",
       subtitle="Engine Displacement across Vehicle Classes")

data(singer, package="lattice")
library(ggplot2)
ggplot(data=singer, aes(x=height)) +
     geom_histogram() +
     facet_wrap(~voice.part, nrow=4) # 4 plots each row, u can pass 8 and have all in one single column.

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

19 Histogram on a categorical variable

library(ggplot2)
theme_set(theme_classic())
# Histogram on a Categorical variable
g <- ggplot(mpg, aes(manufacturer))
g + geom_bar(aes(fill=class), width = 0.5) +
theme(axis.text.x = element_text(angle=65, vjust=0.6)) +
  labs(title="Histogram on Categorical Variable",
       subtitle="Manufacturer across Vehicle Classes")

20 Density plot

library(ggplot2)
theme_set(theme_classic())
# Plot
g <- ggplot(mpg, aes(cty))
g + geom_density(aes(fill=factor(cyl)), alpha=0.8) +
labs(title="Density plot",
subtitle="City Mileage Grouped by Number of cylinders", caption="Source: mpg",
x="City Mileage",
fill="# Cylinders")

21 Box Plot

library(ggplot2) 
theme_set(theme_classic())
# Plot
g <- ggplot(mpg, aes(class, cty))
g + geom_boxplot(varwidth=T, fill="plum") +
labs(title="Box plot",
subtitle="City Mileage grouped by Class of vehicle", caption="Source: mpg",
x="Class of Vehicle",
y="City Mileage")

library(ggthemes)
g <- ggplot(mpg, aes(class, cty))
g + geom_boxplot(aes(fill=factor(cyl))) +
theme(axis.text.x = element_text(angle=65, vjust=0.6)) + 
  labs(title="Box plot",
       subtitle="City Mileage grouped by Class of vehicle",
       caption="Source: mpg",
       x="Class of Vehicle",
       y="City Mileage")

22 Dot_Box Plot

library(ggplot2) 
theme_set(theme_bw())
# plot
g <- ggplot(mpg, aes(manufacturer, cty)) 
g + geom_boxplot() +
geom_dotplot(binaxis='y', stackdir='center',
dotsize = .5,
fill="red") +
theme(axis.text.x = element_text(angle=65, vjust=0.6)) + labs(title="Box plot + Dot plot",
       subtitle="City Mileage vs Class: Each dot represents 1 row in source data",
       caption="Source: mpg",
       x="Class of Vehicle",
       y="City Mileage")

## `stat_bindot()` using `bins = 30`. Pick better value with `binwidth`.

23 Tufte_Boxplot

library(ggthemes)
library(ggplot2)
theme_set(theme_tufte()) # from ggthemes
# plot
g <- ggplot(mpg, aes(manufacturer, cty))
g + geom_tufteboxplot() +
theme(axis.text.x = element_text(angle=65, vjust=0.6)) + 
  labs(title="Tufte Styled Boxplot",
           subtitle="City Mileage grouped by Class of vehicle",
           caption="Source: mpg",
           x="Class of Vehicle",
           y="City Mileage")

24 Violin Plot

library(ggplot2)
theme_set(theme_bw())
# plot
g <- ggplot(mpg, aes(class, cty)) 
g + geom_violin() +
labs(title="Violin plot",
subtitle="City Mileage vs Class of vehicle", caption="Source: mpg",
x="Class of Vehicle",
y="City Mileage")

25 Population Pyramid

library(ggplot2)
library(ggthemes)
options(scipen = 999) # turns of scientific notations like 1e+40
# Read data
email_campaign_funnel <-read.csv("https://raw.githubusercontent.com/shahnp/data/master/email_campaign_funnel.txt")
# X Axis Breaks and Labels
brks <- seq(-15000000, 15000000, 5000000)
lbls = paste0(as.character(c(seq(15, 0, -5), seq(5, 15, 5))), "m")

# Plot
ggplot(email_campaign_funnel, aes(x = Stage, y = Users, fill = Gender)) +
coord_flip() + # Flip axes
labs(title="Email Campaign Funnel") +
  theme_tufte() + # Tufte theme from ggfortify 
  theme(plot.title = element_text(hjust = .5),
axis.ticks = element_blank()) + # Centre plot title 

geom_bar(stat = "identity", width = .6) +
scale_y_continuous(breaks = brks,labels = lbls) +  # Breaks  # Labels
                   
                   scale_fill_brewer(palette = "Dark2") # Color palette

E. Composition

26 Waffle Chart

var <- mpg$class  # the categorical data
## Prep data (nothing to change here)
nrows <- 10
df <- expand.grid(y = 1:nrows, x = 1:nrows)
categ_table <- round(table(var) * ((nrows*nrows)/(length(var))))

df$category <- factor(rep(names(categ_table), categ_table))

# NOTE: if sum(categ_table) is not 100 (i.e. nrows^2), it will need adjustment to make the sum to 100.

## Plot
ggplot(df, aes(x = x, y = y, fill = category)) +
geom_tile(color = "black", size = 0.5) + 
  scale_x_continuous(expand = c(0, 0)) +
  scale_y_continuous(expand = c(0, 0), trans = 'reverse') + 
  scale_fill_brewer(palette = "Set3") +
labs(title="Waffle Chart", subtitle="'Class' of vehicles", caption="Source: mpg") +
theme(panel.border = element_rect(size = 2), plot.title = element_text(size = rel(1.2)), axis.text = element_blank(),
axis.title = element_blank(),
axis.ticks = element_blank(), legend.title = element_blank(), legend.position = "right")

27 Pie Chart

library(ggplot2) 
theme_set(theme_classic())
# Source: Frequency table
df <- as.data.frame(table(mpg$class))
colnames(df) <- c("class", "freq")
pie <- ggplot(df, aes(x = "", y=freq, fill = factor(class))) +
geom_bar(width = 1, stat = "identity") + theme(axis.line = element_blank(),
plot.title = element_text(hjust=0.5)) + labs(fill="class",
       x=NULL,
       y=NULL,
       title="Pie Chart of class",
       caption="Source: mpg")
pie + coord_polar(theta = "y", start=0)

# Source: Categorical variable.
# mpg$class
pie <- ggplot(mpg, aes(x = "", fill = factor(class))) +
geom_bar(width = 1) +
  theme(axis.line = element_blank(),
plot.title = element_text(hjust=0.5)) +
  labs(fill="class",
       x=NULL,
       y=NULL,
       title="Pie Chart of class",
       caption="Source: mpg")
pie + coord_polar(theta = "y", start=0)

28 Treemap

library(devtools)
library(treemapify)
library(ggplot2)
data(G20)

ggplot(G20, aes(area = gdp_mil_usd, fill= region, label = country)) +
 geom_treemap() +
 geom_treemap_text(grow = T, reflow = T, colour = "black") +
 facet_wrap( ~ econ_classification) +
 scale_fill_brewer(palette = "Set1") +
 theme(legend.position = "bottom") +
  labs( title = "The G20 Economies",
        caption = "The area of each country is proportional to its relative GDP within the economic group (advanced or developing)",fill = "Region")

29 Bar Chart

# prep frequency table
freqtable <- table(mpg$manufacturer)
df <- as.data.frame.table(freqtable)

# plot
library(ggplot2)
theme_set(theme_classic())
# Plot
g <- ggplot(df, aes(Var1, Freq))
g + geom_bar(stat="identity", width = 0.5, fill="tomato2") +
labs(title="Bar Chart",
subtitle="Manufacturer of vehicles",
caption="Source: Frequency of Manufacturers from 'mpg' dataset") +
theme(axis.text.x = element_text(angle=65, vjust=0.6))

# From on a categorical column variable

g <- ggplot(mpg, aes(manufacturer))
g + geom_bar(aes(fill=class), width = 0.5) +
theme(axis.text.x = element_text(angle=65, vjust=0.6)) +
  labs(title="Categorywise Bar Chart",
       subtitle="Manufacturer of vehicles",
       caption="Source: Manufacturers from 'mpg' dataset")

30 TimeSeries

31 Line graph

Time Series Plot From a Time Series Object (ts)

## From Timeseries object (ts) 
library(ggplot2) 
library(ggfortify)
theme_set(theme_classic())
# Plot
autoplot(AirPassengers) +
labs(title="AirPassengers") +
  theme(plot.title = element_text(hjust=0.5))

library(ggplot2) 
theme_set(theme_classic())
# Allow Default X Axis Labels 
ggplot(economics, aes(x=date)) +
geom_line(aes(y=returns_perc)) + labs(title="Time Series Chart",
       subtitle="Returns Percentage from 'Economics' Dataset",
       caption="Source: Economics",
       y="Returns %") # Default X Axis Labels

# LINE GRAPH

library(ggplot2)
library(lubridate)

## 
## Attaching package: 'lubridate'

## The following object is masked from 'package:base':
## 
##     date

theme_set(theme_bw())
economics_m <- economics[1:24, ]
# labels and breaks for X axis text
lbls <- paste0(month.abb[month(economics_m$date)], " ",lubridate::year(economics_m$date))
brks <- economics_m$date
# plot
ggplot(economics_m, aes(x=date)) +
geom_line(aes(y=returns_perc)) +
  labs(title="Monthly Time Series",
       subtitle="Returns Percentage from Economics Dataset",
       caption="Source: Economics",
       y="Returns %") +  # title and caption
  scale_x_date(labels = lbls, breaks = brks) + # change to monthly ticks and labels
  theme(axis.text.x = element_text(angle = 90, vjust=0.5), # rotate x axis text
        panel.grid.minor = element_blank()) # turn off minor grid

#

library(ggplot2) 
library(lubridate)
theme_set(theme_bw())
economics_y <- economics[1:90, ]
# labels and breaks for X axis text
brks <- economics_y$date[seq(1, length(economics_y$date), 12)] 
lbls <- lubridate::year(brks)
# plot
ggplot(economics_y, aes(x=date)) +
geom_line(aes(y=returns_perc)) +
  labs(title="Yearly Time Series",
       subtitle="Returns Percentage from Economics Dataset",
       caption="Source: Economics",
       y="Returns %") +  # title and caption
scale_x_date(labels = lbls,
breaks = brks) + # change to monthly ticks and labels
theme(axis.text.x = element_text(angle = 90, vjust=0.5), # rotate x axis text
      panel.grid.minor = element_blank()) # turn off minor grid

Time Series Plot From Long Data Format: Multiple Time Series in Same Dataframe Column Time Series Plot From Wide Data Format: Data in Multiple Columns of Dataframe

32 Multiple line graph

data(economics_long, package = "ggplot2")

library(ggplot2) 
library(lubridate)
theme_set(theme_bw())
df <- economics_long[economics_long$variable %in% c("psavert", "uempmed"), ] 
df <- df[lubridate::year(df$date) %in% c(1967:1981), ]
# labels and breaks for X axis text
brks <- df$date[seq(1, length(df$date), 12)]
lbls <- lubridate::year(brks)
# plot
ggplot(df, aes(x=date)) +
geom_line(aes(y=value, col=variable)) +
  labs(title="Time Series of Returns Percentage",
       subtitle="Drawn from Long Data format",
       caption="Source: Economics",
       y="Returns %",
       color=NULL) +  # title and caption
scale_x_date(labels = lbls, breaks = brks) + # change to monthly ticks and labels
  scale_color_manual(labels = c("psavert", "uempmed"),
values = c("psavert"="#00ba38", "uempmed"="#f8766d")) + # line color 
  theme(axis.text.x = element_text(angle = 90, vjust=0.5, size = 8), # rotate x axis text
panel.grid.minor = element_blank()) # turn off minor grid

# Time Series Plot From Wide Data Format: Data in Multiple Columns of Dataframe.

library(ggplot2)
library(lubridate)
theme_set(theme_bw())
df <- economics[, c("date", "psavert", "uempmed")]
df <- df[lubridate::year(df$date) %in% c(1967:1981), ]
# labels and breaks for X axis text
brks <- df$date[seq(1, length(df$date), 12)] 
lbls <- lubridate::year(brks)
# plot
ggplot(df, aes(x=date)) +
geom_line(aes(y=psavert, col="psavert")) +
  geom_line(aes(y=uempmed, col="uempmed")) +
  labs(title="Time Series of Returns Percentage",
       subtitle="Drawn From Wide Data format",
caption="Source: Economics", y="Returns %") + # title and caption
  scale_x_date(labels = lbls, breaks = brks) + # change to monthly ticks and labels
  scale_color_manual(name="",
values = c("psavert"="#00ba38", "uempmed"="#f8766d")) + # line color
  theme(panel.grid.minor = element_blank()) # turn off minor grid

33 Stacked Area Chart

library(ggplot2) 
library(lubridate)
theme_set(theme_bw())
df <- economics[, c("date", "psavert", "uempmed")]
df <- df[lubridate::year(df$date) %in% c(1967:1981), ]
# labels and breaks for X axis text
brks <- df$date[seq(1, length(df$date), 12)] 
lbls <- lubridate::year(brks)

# plot
ggplot(df, aes(x=date)) +
geom_area(aes(y=psavert+uempmed, fill="psavert")) + 
  geom_area(aes(y=uempmed, fill="uempmed")) +
  labs(title="Area Chart of Returns Percentage",
       subtitle="From Wide Data format",
       caption="Source: Economics",
       y="Returns %") +  # title and caption
scale_x_date(labels = lbls, breaks = brks) + # change to monthly ticks and labels
  scale_fill_manual(name="",
values = c("psavert"="#00ba38", "uempmed"="#f8766d")) + # line color
  theme(panel.grid.minor = element_blank()) # turn off minor grid

34 Calendar Heatmap

# http://margintale.blogspot.in/2012/04/ggplot2-time-series-heatmaps.html 
library(ggplot2)
library(plyr)
library(scales)
library(zoo)

df <- read.csv("https://raw.githubusercontent.com/shahnp/data/master/yahoo.txt")
df$date <- as.Date(df$date) # format date
df <- df[df$year >= 2012, ] # filter reqd years


# Create Month Week
df$yearmonth <- as.yearmon(df$date)
df$yearmonthf <- factor(df$yearmonth)
df <- ddply(df,.(yearmonthf), transform, monthweek=1+week-min(week)) # compute week numbe r of month
df <- df[, c("year", "yearmonthf", "monthf", "week", "monthweek", "weekdayf", "VIX.Close" )]

# Plot
ggplot(df, aes(monthweek, weekdayf, fill = VIX.Close)) +
geom_tile(colour = "white") +
  facet_grid(year~monthf) + 
  scale_fill_gradient(low="red", high="green") + 
  labs(x="Week of Month",
       y="",
       title = "Time-Series Calendar Heatmap",
       subtitle="Yahoo Closing Price",
       fill="Close")

35 Slope Chart

library(dplyr)
theme_set(theme_classic())
source_df <- read.csv("https://raw.githubusercontent.com/shahnp/data/master/cancer_survival_rates.txt")

# Define functions. Source: https://github.com/jkeirstead/r-slopegraph
tufte_sort <- function(df, x="year", y="value", group="group", method="tufte", min.space=
0.05) {
## First rename the columns for consistency 
ids <- match(c(x, y, group), names(df))
df <- df[,ids]
names(df) <- c("x", "y", "group")
## Expand grid to ensure every combination has a defined value 
tmp <- expand.grid(x=unique(df$x), group=unique(df$group))
tmp <- merge(df, tmp, all.y=TRUE)
df <- mutate(tmp, y=ifelse(is.na(y), 0, y))
## Cast into a matrix shape and arrange by first column 
require(reshape2)
tmp <- dcast(df, group ~ x, value.var="y")
ord <- order(tmp[,2])
tmp <- tmp[ord,]
min.space <- min.space*diff(range(tmp[,-1]))
yshift <- numeric(nrow(tmp))
## Start at "bottom" row
## Repeat for rest of the rows until you hit the top 
for (i in 2:nrow(tmp)) {
## Shift subsequent row up by equal space so gap between ## two entries is >= minimum
mat <- as.matrix(tmp[(i-1):i, -1])
d.min <- min(diff(mat))
yshift[i] <- ifelse(d.min < min.space, min.space - d.min, 0) }

tmp <- cbind(tmp, yshift=cumsum(yshift))
scale <- 1

## Store these gaps in a separate variable so that they can be scaled ypos = a*yshift +y
tmp <- melt(tmp, id=c("group", "yshift"), variable.name="x", value.name="y")
tmp <- transform(tmp, ypos=y + scale*yshift)
return(tmp)
}

plot_slopegraph <- function(df) {
ylabs <- subset(df, x==head(x,1))$group 
yvals <- subset(df, x==head(x,1))$ypos
fontSize <- 3
gg <- ggplot(df,aes(x=x,y=ypos)) +
geom_line(aes(group=group),colour="grey80") + geom_point(colour="white",size=8) +
geom_text(aes(label=y), size=fontSize, family="American Typewriter") + scale_y_continuous(name="", breaks=yvals, labels=ylabs)
return(gg) 
}

## Prepare data
df <- tufte_sort(source_df,
                 x="year",
                 y="value",
                 group="group",
                 method="tufte",
                 min.space=0.05)
df <- transform(df,
x=factor(x, levels=c(5,10,15,20),
labels=c("5 years","10 years","15 years","20 years")),
y=round(y))

## Plot
plot_slopegraph(df) + labs(title="Estimates of % survival rates") +
theme(axis.title=element_blank(), axis.ticks = element_blank(), plot.title = element_text(hjust=0.5,family = "American Typewriter",face="bold"),axis.text = element_text(family = "American Typewriter", face="bold"))

36 Seasonal line Chart

library(ggplot2)
library(forecast)
theme_set(theme_classic())
# Subset data
nottem_small <- window(nottem, start=c(1920, 1), end=c(1925, 12)) # subset a smaller time window
# Plot
ggseasonplot(AirPassengers) + labs(title="Seasonal plot: International Airline Passengers" )

ggseasonplot(nottem_small) + labs(title="Seasonal plot: Air temperatures at Nottingham Cas tle")

37 Hierarchical Dendrogram

#install.packages("ggdendro")
library(ggplot2) 
library(ggdendro)
theme_set(theme_bw())
hc <- hclust(dist(USArrests), "ave") # hierarchical clustering
# plot
ggdendrogram(hc, rotate = TRUE, size = 2)

38 Clusters

library(ggplot2)
library(ggalt)
library(ggfortify) 
theme_set(theme_classic())
# Compute data with principal components ------------------ 
df <- iris[c(1, 2, 3, 4)]
pca_mod <- prcomp(df) # compute principal components
# Data frame of principal components ----------------------
df_pc <- data.frame(pca_mod$x, Species=iris$Species) # dataframe of principal components
df_pc_vir <- df_pc[df_pc$Species == "virginica", ] # df for 'virginica'
df_pc_set <- df_pc[df_pc$Species == "setosa", ] # df for 'setosa'
df_pc_ver <- df_pc[df_pc$Species == "versicolor", ] # df for 'versicolor'
# Plot ----------------------------------------------------
ggplot(df_pc, aes(PC1, PC2, col=Species)) +
geom_point(aes(shape=Species), size=2) + # draw points 
  labs(title="Iris Clustering",
       subtitle="With principal components PC1 and PC2 as X and Y axis",
caption="Source: Iris") +
coord_cartesian(xlim = 1.2 * c(min(df_pc$PC1), max(df_pc$PC1)),
ylim = 1.2 * c(min(df_pc$PC2), max(df_pc$PC2))) + # change axis limits
geom_encircle(data = df_pc_vir, aes(x=PC1, y=PC2)) + # draw circles
geom_encircle(data = df_pc_set, aes(x=PC1, y=PC2)) +
geom_encircle(data = df_pc_ver, aes(x=PC1, y=PC2))

39 Network Visulization

library(ggplot2)
library(ggnetwork)
library(geomnet)
library(network)

## Warning: package 'network' was built under R version 3.5.2

## network: Classes for Relational Data
## Version 1.15 created on 2019-04-01.
## copyright (c) 2005, Carter T. Butts, University of California-Irvine
##                     Mark S. Handcock, University of California -- Los Angeles
##                     David R. Hunter, Penn State University
##                     Martina Morris, University of Washington
##                     Skye Bender-deMoll, University of Washington
##  For citation information, type citation("network").
##  Type help("network-package") to get started.

## 
## Attaching package: 'network'

## The following object is masked from 'package:plyr':
## 
##     is.discrete

# make the data available
data(madmen, package = 'geomnet')
# create undirected network
mm.net <- network(madmen$edges[, 1:2],directed = FALSE)
# mm.net # glance at network object
# create node attribute (gender)
rownames(madmen$vertices) <- madmen$vertices$label
mm.net %v% "gender" <- as.character(madmen$vertices[ network.vertex.names(mm.net),"Gender"])
# gender color palette
mm.col <- c("female" = "#ff0000", "male" = "#00ff00")
set.seed(10052016)
ggplot(data = ggnetwork(mm.net, layout = "kamadakawai"),aes(x, y, xend = xend, yend =yend)) +
  geom_edges(color = "grey50") + # draw edge layer
  geom_nodes(aes(colour = gender), size = 2) + # draw node layer
  geom_nodetext(aes(colour = gender,
     label = vertex.names),
            size = 3, vjust = -0.6) + # draw node label layer
  scale_colour_manual(values = mm.col) +
  xlim(c(-0.05, 1.05)) +
  theme_blank() +
  theme(legend.position = "bottom")

## Loading required package: sna

## Loading required package: statnet.common

## Warning: package 'statnet.common' was built under R version 3.5.2

## 
## Attaching package: 'statnet.common'

## The following object is masked from 'package:base':
## 
##     order

## sna: Tools for Social Network Analysis
## Version 2.4 created on 2016-07-23.
## copyright (c) 2005, Carter T. Butts, University of California-Irvine
##  For citation information, type citation("sna").
##  Type help(package="sna") to get started.

40 Multiple Graphs per Page

data(Salaries, package="car")

## Warning in data(Salaries, package = "car"): data set 'Salaries' not found

library(ggplot2)
p1 <- ggplot(data=mpg, aes(x=hwy)) + geom_bar()
p2 <- ggplot(data=mpg, aes(x=trans)) + geom_bar()
p3 <- ggplot(data=mpg, aes(x=hwy, y=cty)) + geom_point()

library(gridExtra)
grid.arrange(p1, p2, p3, ncol=3)

41 Parallel Coordinate Plots

library(triangle)
set.seed(0)
q1_d1 <- round(rtriangle(1000, 1, 7, 5))
q1_d2 <- round(rtriangle(1000, 1, 7, 6))
q1_d3 <- round(rtriangle(1000, 1, 7, 2))
df <- data.frame(q1_d1 = factor(q1_d1),
                 q1_d2 = factor(q1_d2), 
                 q1_d3 = factor(q1_d3))

library(dplyr)
# group by combinations and count
df_grouped <- df %>% group_by(q1_d1,q1_d2, q1_d3) %>% count()

# set an id string that denotes the value combination
df_grouped <- df_grouped %>% mutate(id = factor(paste(q1_d1, q1_d2, q1_d3, sep = '-')))
order.freq <- order(df_grouped[,4],decreasing=TRUE)

# sort by count and select top rows
df_grouped <- df_grouped[order.freq[1:25],]

library(reshape2)
library(ggplot2)
# create long format
df_pcp <- melt(df_grouped, id.vars =c('id', 'n'))
df_pcp$value <- factor(df_pcp$value)

y_levels <- levels(factor(1:7))

ggplot(df_pcp, aes(x = variable, y = value, group = id)) + # group = id is important!
  geom_path(aes(size = n, color = id), alpha = 0.5, lineend = 'round', linejoin ='round') +
  scale_y_discrete(limits = y_levels, expand = c(0.5, 0)) +
  scale_size(breaks = NULL, range = c(1,7))

42 Rug_boxplot

library(ggplot2)
ggplot(mpg, aes(x=cty, y=hwy)) +
     geom_boxplot(fill="cornflowerblue", color="black", notch=TRUE)+
     geom_point(position="jitter",color="blue", alpha=.5)+
     geom_rug(side="l", color="black")

43 Saving Graphs

The available formats include .ps, .tex, .jpeg, .pdf, .jpg, .tiff, .png, .bmp, .svg, or .wmf (the latter only being available on Windows machines).

SAVE the graph

# png
knitr::opts_chunk$set(fig.width=7,fig.height=4)

myplot <- ggplot(data=mtcars,aes(x=mpg)) +
  geom_histogram(bins = 30)
ggsave(file="mygraph.png", plot=myplot,width=5, height=4)

# PDF

ggplot(data=mtcars, aes(x=mpg)) +
   geom_histogram()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggsave(file="mygraph.pdf")

## Saving 8 x 6 in image
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.